INDEX
Explanations
No Explanations Found
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
674
+0.29
1.0%
1253
+0.07
0.3%
1120
+0.06
0.2%
Correlated Neurons
Index
P. Corr.
Cos Sim.
2
-0.29
0.00
0
-0.07
0.00
1
-0.06
0.00
Negative Logits
unspeak
-2.82
reluct
-2.66
shenan
-2.62
horrend
-2.55
ineffec
-2.53
apprehen
-2.47
impra
-2.35
unavoid
-2.33
laug
-2.31
vainly
-2.29
POSITIVE LOGITS
<bos>
9.89
GEBURTSDATUM
2.23
expandindo
2.08
Autoritní
2.01
betweenstory
1.96
Walkover
1.89
Италијани
1.88
-------------</
1.85
'\\;'
1.83
Paglinawan
1.81
Activations Density 0.000%
No Known Activations
This feature has no known activations.